Back to directory

dsh-mnemosyne

In a curated listMaintenance: Active

canyuey/dsh-mnemosyne

Adds durable evidence-backed memory tools to DSH through a Python Memory Node, REST/MCP client, session capture, and fail-closed preset guard.

View on GitHubHomepage
$ dsh plugin --profile web add github:canyueY/dsh-mnemosyne#main

19

stars

1

forks

Python

Language

Apache-2.0

License

2026-10-28

Created

2026-11-10

Last push

Keep agent memory with evidence and retrieval across tasks. A persistent Memory Bank, with a DSH adapter that starts/guards the Node and registers `memory_*` tools.

DSH integration

Native runtime

Author-claimed

Safety audit

Unaudited

Last verified

2026-11-09

License

Apache-2.0

01What can it help you accomplish?

  • Keep agent memory with evidence and retrieval across tasks

    A persistent Memory Bank, with a DSH adapter that starts/guards the Node and registers `memory_*` tools

    DeepSeek Harness users who need this workflow

02How to install into DeepSeek Harness

Installation steps

  1. 01

    Install the DSH adapter with `dsh plugin --profile web add github:canyueY/dsh-mnemosyne#main`. The README also provides a standalone distribution package.

    $ dsh plugin --profile web add github:canyueY/dsh-mnemosyne#main

Verify the integration

  • After upgrading, confirm the data directory is still `%LOCALAPPDATA%\Mnemosyne Memory Bank` and REST remains `/api/v1`.

Rollback

  • For the old DSH plugin, use tag `legacy/dsh-plugin-0.2.0` or the archived directory.

03DSH integration and capability boundaries

DSH integrationNative runtime

DSH integration documented in the repository README

  • Independent memory service with DSH adapter

    A persistent Memory Bank, with a DSH adapter that starts/guards the Node and registers `memory_*` tools

04Who is it for? When not to use it?

Good for

  • DeepSeek Harness users who need this workflow

Not for

  • Structure discovery, hypothesis generation, strategy learning and controlled self-evolution are roadmap items, not delivered capabilities.
  • Use a Bank for project isolation and multiple Nodes for cross-device use; do not give two systems write authority over the same long-term cognition.

05Compatibility, maintenance and safety notes

  • Structure discovery, hypothesis generation, strategy learning and controlled self-evolution are roadmap items, not delivered capabilities.
  • Use a Bank for project isolation and multiple Nodes for cross-device use; do not give two systems write authority over the same long-term cognition.
2026-10-282026-11-04standalone-2.0.0

Repository README statements; no independent safety audit.

06Frequently asked questions

How do I install it in DeepSeek Harness?

Install the DSH adapter with `dsh plugin --profile web add github:canyueY/dsh-mnemosyne#main`. The README also provides a standalone distribution package.

What does it add to my DSH workflow?

A persistent Memory Bank, with a DSH adapter that starts/guards the Node and registers `memory_*` tools

What limitation should I know before enabling it?

Structure discovery, hypothesis generation, strategy learning and controlled self-evolution are roadmap items, not delivered capabilities. Use a Bank for project isolation and multiple Nodes for cross-device use; do not give two systems write authority over the same long-term cognition.

08Data and sources

  • Author-claimedgithub.com796dc2923676…

    它可以作为独立记忆系统运行,也可以通过适配器接入 DeepSeek Harness(DSH)等 Agent 宿主。

This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-11-09. Found an error? Submit a correction.

🏆

Best DeepSeek Harness Plugins

Twelve plugins worth installing first — picked from the whole catalog, across every category.

DSH Plugins is an independent community directory of DeepSeek Harness plugins. Not affiliated with or endorsed by DeepSeek. Third-party plugins are not security-audited — review the source before installing.

New DeepSeek Harness plugins, weekly. No spam.